Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1164 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.6290. Min Act: -0.0000

Data Index: 759082 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5348. Min Act: -0.0000

Data Index: 1331001 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1146836 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4985. Min Act: -0.0000

Data Index: 590606 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4458. Min Act: -0.0000

Data Index: 311782 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4317. Min Act: -0.0000

Data Index: 437832 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4374. Min Act: -0.0000

Data Index: 55730 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4122. Min Act: -0.0000

Data Index: 463600 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4130. Min Act: -0.0000

Data Index: 884605 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4088. Min Act: -0.0000

Data Index: 891576 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4008. Min Act: -0.0000

Data Index: 433224 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.3993. Min Act: -0.0000

Data Index: 693123 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4087. Min Act: -0.0000

Data Index: 362423 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.3951. Min Act: -0.0000

Data Index: 401341 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.3887. Min Act: -0.0000

Data Index: 702396 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.3742. Min Act: -0.0000

Data Index: 7911 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.3695. Min Act: -0.0000

Data Index: 969787 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.3792. Min Act: -0.0000

Data Index: 730387 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.3790. Min Act: 0.0000

Data Index: 246441 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1183950 (C4 (Web Text))

Max Activating Token Index: 283